R Notebook

if(!require("plotly")) {install.packages("plotly")}

# install.packages("latex2exp")
# install.packages("BiocManager") 
# install.packages("corrplot")
# BiocManager::install("EBImage")

if(!require("lme4")){install.packages("lme4")}
if(!require("lmerTest")){install.packages("lmerTest")}
if(!require("nlme")){install.packages("nlme")}
if(!require("formattable")){install.packages("formattable")}
if(!require("xgboost")){install.packages("xgboost")}
if(!require("processx")) {install.packages("processx")}

if(!require("mefa")){install.packages("mefa")}

library(plotly)
library(lme4)
library(lmerTest)
library(nlme)
library(formattable)
library(xgboost)

### Load libraries
library(EBImage)
library(ggplot2)
library(stringr)
library(gridExtra)
library(latex2exp)
packageVersion('plotly')

[1] ‘4.9.1’

Sys.setenv("plotly_username"="thuynh32")
Sys.setenv("plotly_api_key"="xcSv1yzujDc1IGEwQlr2")

drive1 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_1_PP.csv')
drive2 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_2_PP.csv')
drive3 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_3_PP.csv')
drive4 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_4_PP.csv', stringsAsFactors = T)

dfSeg <- data.frame(rep(1, nrow(drive4)), rep(2, nrow(drive4)), rep(3, nrow(drive4)), rep(4, nrow(drive4)))
names(dfSeg) <- c("Seg1", "Seg2", "Seg3", "Seg4")

combinedDf_Seg1 <- cbind(drive4, 
                    drive1$MeanPP_Seg0, 
                    drive2$MeanPP_Seg1, drive3$MeanPP_Seg1, 
                    drive2$MeanPP_Seg0, drive3$MeanPP_Seg0,
                    drive2$StdPP, drive3$StdPP,
                    dfSeg$Seg1
                  )
combinedDf_Seg2 <- cbind(drive4, 
                    drive1$MeanPP_Seg0, 
                    drive2$MeanPP_Seg2, drive3$MeanPP_Seg2, 
                    drive2$MeanPP_Seg0, drive3$MeanPP_Seg0,
                    drive2$StdPP, drive3$StdPP,
                    dfSeg$Seg2
                  )
combinedDf_Seg3 <- cbind(drive4, 
                    drive1$MeanPP_Seg0, 
                    drive2$MeanPP_Seg3, drive3$MeanPP_Seg3, 
                    drive2$MeanPP_Seg0, drive3$MeanPP_Seg0,
                    drive2$StdPP, drive3$StdPP,
                    dfSeg$Seg3
                  )
combinedDf_Seg4 <- cbind(drive4, 
                    drive1$MeanPP_Seg0, 
                    drive2$MeanPP_Seg4, drive3$MeanPP_Seg4, 
                    drive2$MeanPP_Seg0, drive3$MeanPP_Seg0,
                    drive2$StdPP, drive3$StdPP,
                    dfSeg$Seg4
                  )

names(combinedDf_Seg1) <- c(names(drive4), 
                       "PP_Dev_1_Turning",
                       "PP_Dev_2_Straight", "PP_Dev_3_Straight", 
                       "PP_Dev_2_Turning", "PP_Dev_3_Turning", 
                       "Std_PP_2", "Std_PP_3", "Segment")
names(combinedDf_Seg2) <- c(names(drive4), 
                       "PP_Dev_1_Turning",
                       "PP_Dev_2_Straight", "PP_Dev_3_Straight", 
                       "PP_Dev_2_Turning", "PP_Dev_3_Turning", 
                       "Std_PP_2", "Std_PP_3", "Segment")
names(combinedDf_Seg3) <- c(names(drive4), 
                       "PP_Dev_1_Turning",
                       "PP_Dev_2_Straight", "PP_Dev_3_Straight", 
                       "PP_Dev_2_Turning", "PP_Dev_3_Turning", 
                       "Std_PP_2", "Std_PP_3", "Segment")
names(combinedDf_Seg4) <- c(names(drive4), 
                       "PP_Dev_1_Turning",
                       "PP_Dev_2_Straight", "PP_Dev_3_Straight", 
                       "PP_Dev_2_Turning", "PP_Dev_3_Turning", 
                       "Std_PP_2", "Std_PP_3", "Segment")

combinedDf_Seg1$Subject <- paste0(as.factor(combinedDf_Seg1$Subject), ".S1")
combinedDf_Seg2$Subject <- paste0(as.factor(combinedDf_Seg2$Subject), ".S2")
combinedDf_Seg3$Subject <- paste0(as.factor(combinedDf_Seg3$Subject), ".S3")
combinedDf_Seg4$Subject <- paste0(as.factor(combinedDf_Seg4$Subject), ".S4")

combinedDf <- rbind(combinedDf_Seg1, combinedDf_Seg2, combinedDf_Seg3, combinedDf_Seg4)

combinedDf$Subject <- paste0("#", str_pad(combinedDf$Subject, 2, pad="0"))
combinedDf$Segment <- as.factor(combinedDf$Segment)

combinedDf_NoStressor <- combinedDf[combinedDf$Activity == "NO",]
combinedDf_Cognitive <- combinedDf[combinedDf$Activity == "C",]
combinedDf_Motoric <- combinedDf[combinedDf$Activity == "M",]

# combinedDf_NoStressor$Subject <- as.factor(combinedDf_NoStressor$Subject)
# combinedDf_Cognitive$Subject <- as.factor(combinedDf_Cognitive$Subject)
# combinedDf_Motoric$Subject <- as.factor(combinedDf_Motoric$Subject)

COLOR_NORMAL <- list(color='rgb(120,120,120)')
COLOR_COGNITIVE <- list(color='rgb(158,202,225)')
COLOR_MOTORIC <- list(color='rgb(58,200,225)')
COLOR_FAILURE <- list(color='red')

THRESHOLD_MILD = 0.07
THRESHOLD_EXTREME = 0.2

MARKER_LINE_MILD = list(color="blue")
MARKER_LINE_EXTREME = list(color="red")

yAxis <- list(title = 'Perinasal Perspiration (Log)', range=c(-0.3, 0.5))

fig_NoStressor <- plot_ly(combinedDf_NoStressor, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#1.S1", xend="#7.S4", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#01", xend="#41", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group=No Stressor")

htmltools::tagList(fig_NoStressor)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

yAxis <- list(title = 'Perinasal Perspiration (Log)', range=c(-0.3, 0.3))

fig_Cognitive <- plot_ly(combinedDf_Cognitive, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#12.S1", xend="#3.S4", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#02", xend="#22", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group=Cognitive")

htmltools::tagList(fig_Cognitive)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

yAxis <- list(title = 'Perinasal Perspiration (Log)', range=c(-0.3, 0.5))

fig_Motoric <- plot_ly(combinedDf_Motoric, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#24.S1", xend="#9.S4", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#05", xend="#31", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group: Motoric")

htmltools::tagList(fig_Motoric)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

library(nlme)

combinedDf$Subject = as.factor(combinedDf$Subject)
combinedDf$Activity = as.factor(combinedDf$Activity)

combinedDf$PP_Dev_Group = ifelse(combinedDf$PP_Dev > THRESHOLD_MILD, 1, 0)

model = lme(PP_Dev ~ 
              abs(PP_Dev_2_Straight)
              + abs(PP_Dev_3_Straight)
              + abs(PP_Dev_2_Turning) 
              + abs(PP_Dev_3_Turning)
              + factor(Activity), 
            random=~1|Subject,
            data=combinedDf,
            method="REML")

# anova(model)
summary(model)

Linear mixed-effects model fit by REML
 Data: combinedDf 

Random effects:
 Formula: ~1 | Subject
        (Intercept)   Residual
StdDev:  0.07378811 0.02767054

Fixed effects: PP_Dev ~ abs(PP_Dev_2_Straight) + abs(PP_Dev_3_Straight) + abs(PP_Dev_2_Turning) +      abs(PP_Dev_3_Turning) + factor(Activity) 

 Correlation: 
                       (Intr) a(PP_D_2_S a(PP_D_3_S a(PP_D_2_T a(PP_D_3_T fc(A)M
abs(PP_Dev_2_Straight)  0.255                                                   
abs(PP_Dev_3_Straight) -0.008 -0.137                                            
abs(PP_Dev_2_Turning)  -0.240 -0.570     -0.341                                 
abs(PP_Dev_3_Turning)  -0.556 -0.161     -0.456      0.053                      
factor(Activity)M      -0.421 -0.082      0.073     -0.177      0.062           
factor(Activity)NO     -0.279 -0.023      0.305     -0.389     -0.102      0.544

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max 
-0.62224161 -0.30808560  0.03485727  0.22938155  0.62177482 

Number of Observations: 84
Number of Groups: 84 

plot(model)

model = lme(PP_Dev ~ 
              abs(PP_Dev_2_Turning)
              + factor(Activity), 
            random=~1|Subject,
            data=combinedDf,
            method="REML")

# anova(model)
summary(model)

Linear mixed-effects model fit by REML
 Data: combinedDf 

Random effects:
 Formula: ~1 | Subject
        (Intercept)   Residual
StdDev:  0.07514543 0.02817954

Fixed effects: PP_Dev ~ abs(PP_Dev_2_Turning) + factor(Activity) 

 Correlation: 
                      (Intr) a(PP_D fc(A)M
abs(PP_Dev_2_Turning) -0.497              
factor(Activity)M     -0.457 -0.270       
factor(Activity)NO    -0.346 -0.423  0.550

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max 
-0.53252940 -0.23585738  0.02008019  0.22292732  0.55040771 

Number of Observations: 84
Number of Groups: 84 

plot(model)

model = lme(PP_Dev ~ 
              PP_Dev_2_Straight + 
              PP_Dev_3_Straight + 
              PP_Dev_1_Turning + 
              PP_Dev_2_Turning + 
              PP_Dev_3_Turning + 
              Std_PP_2 + 
              Std_PP_3 +
              factor(Activity), 
            random=~1|Subject,
            data=combinedDf,
            method="REML")

# anova(model)
summary(model)

Linear mixed-effects model fit by REML
 Data: combinedDf 

Random effects:
 Formula: ~1 | Subject
        (Intercept)   Residual
StdDev:  0.07042784 0.02641044

Fixed effects: PP_Dev ~ PP_Dev_2_Straight + PP_Dev_3_Straight + PP_Dev_1_Turning +      PP_Dev_2_Turning + PP_Dev_3_Turning + Std_PP_2 + Std_PP_3 +      factor(Activity) 

 Correlation: 
                   (Intr) PP_D_2_S PP_D_3_S PP_D_1 PP_D_2_T PP_D_3_T S_PP_2 S_PP_3 fc(A)M
PP_Dev_2_Straight  -0.157                                                                
PP_Dev_3_Straight   0.048 -0.217                                                         
PP_Dev_1_Turning   -0.818  0.257    0.106                                                
PP_Dev_2_Turning    0.445 -0.777    0.007   -0.487                                       
PP_Dev_3_Turning   -0.164  0.280   -0.639   -0.197 -0.358                                
Std_PP_2            0.261 -0.458   -0.156   -0.367  0.743   -0.173                       
Std_PP_3           -0.846  0.398    0.057    0.750 -0.721    0.160   -0.640              
factor(Activity)M   0.182 -0.232    0.340   -0.129  0.171   -0.267    0.108 -0.347       
factor(Activity)NO -0.251 -0.074    0.268    0.163 -0.194   -0.101   -0.368  0.263  0.394

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max 
-0.67464572 -0.25005516  0.08544853  0.18066413  0.65739692 

Number of Observations: 84
Number of Groups: 84 

plot(model)

Machine Learning

combinedDf$PP_Dev <- NULL

combinedDf$Subject <- NULL
combinedDf$Activity_NO <- ifelse(combinedDf$Activity == "NO", 1, 0)
combinedDf$Activity_C <- ifelse(combinedDf$Activity == "C", 1, 0)
combinedDf$Activity_M <- ifelse(combinedDf$Activity == "M", 1, 0)
combinedDf$Activity <- NULL

combinedDf$InSegment1 <- ifelse(combinedDf$Segment == 1, 1, 0)
combinedDf$InSegment2 <- ifelse(combinedDf$Segment == 2, 1, 0)
combinedDf$InSegment3 <- ifelse(combinedDf$Segment == 3, 1, 0)
combinedDf$InSegment4 <- ifelse(combinedDf$Segment == 4, 1, 0)
combinedDf$Segment <- NULL

combinedDf$Class <- ifelse(combinedDf$PP_Dev_Group == 1, T, F)
combinedDf$PP_Dev_Group <- NULL

# library(mefa)
# combinedDf <- rep(combinedDf, 10) 

# s=55, f=4

set.seed(5151) 
n_folds <- 5
params <- param <- list(objective   = "binary:logistic", 
               booster          = "gbtree",
               eval_metric      = "auc",
               eta              = 0.1,
               max_depth        = 8,
               alpha            = 1,
               lambda           = 0,
               gamma            = 0.3,
               min_child_weight = 0.3,
               subsample        = 1,
               colsample_bytree = 0.5)
           
# xgb_m <- xgb.cv(   params               = param,
#                   data = as.matrix(combinedDf %>% select(-Class)) ,
#                   label =  combinedDf$Class,
#                   nrounds             = 100,
#                   verbose             = F,
#                   prediction          = T,
#                   maximize            = T,
#                   nfold = n_folds,
#                   metrics  = "auc",
#                   early_stopping_rounds = 100,
#                   stratified       = F,
#                   scale_pos_weight = 0.5)
# 
# # xgb_m$evaluation_log[xgb_m$best_iteration,"test_auc_mean"]
# xgb_m$evaluation_log[xgb_m$best_iteration,]

# Error       
ml_data <- as.matrix(combinedDf %>% select(-Class))

xgb_m <- xgb.cv(   params               = param,
                  data = ml_data ,
                  label =  combinedDf$Class,
                  nrounds             = 500,
                  verbose             = F,
                  prediction          = T,
                  maximize            = T,
                  nfold               = n_folds,
                  metrics             = c("auc", "error"),
                  early_stopping_rounds = 100,
                  stratified            = F,
                  scale_pos_weight      = 3.05)

# xgb_m$evaluation_log[xgb_m$best_iteration,"test_auc_mean"]
xgb_m$evaluation_log[xgb_m$best_iteration,]

NA

library(pROC)

# it = which.max(xgb_m$evaluation_log$test_auc_mean)
# best.iter = xgb_m$evaluation_log$iter[it]
# best.iter 

plot(pROC::roc(response = ifelse(combinedDf$Class==T, 1, 0),
               predictor = xgb_m$pred,
               levels=c(0, 1)),
     lwd=1.5) 

Setting direction: controls < cases